Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (7): 84-86.

• 学术探讨 • Previous Articles     Next Articles

An Improved Particle Swarm Optimization Algorithm with disturbance term

QingYuan He   

  • Received:2006-04-04 Revised:1900-01-01 Online:2007-03-01 Published:2007-03-01
  • Contact: QingYuan He

带有扰动项的改进粒子群算法

何庆元 韩传久   

  1. 桂林电子工业学院 图像信号研究所 桂林电子工业学院计算机系
  • 通讯作者: 何庆元

Abstract: The particle swarm optimization (PSO) algorithm, existing improvements about it and their influence on PSO performance are introduced. The framework of PSO basic formula is analyzed. Implied by its three-term structure, the inherent shortcoming that trends to local optima is indicated. Then a modified velocity updating formula of particle swarm optimization algorithm is declared. The addition of the disturbance term based on existing structure effectively mends the defects. The convergence of the improved algorithm is analyzed. Simulation results demonstrated that the improved algorithm have more remarkable performance than the former one.

Key words: Particle Swarm Optimization, convergence, local optima, disturbance term

摘要: 在介绍基本粒子群优化(PSO)算法及其现有一些改进的基础上,分析了PSO算法更新公式的固有缺陷。指出其三段式结构所隐含的易陷入局部最优问题,进而提出了一种带有扰动项的改进粒子群算法(PSO-DT)。它改变了现有算法的速度更新公式,加入了用于避免陷入局部最优的扰动项。分析了该改进算法的收敛性。测试表明,改进算法在优化性能上有较大提高

关键词: 粒子群优化算?, 收敛性, 局部最优, 扰动项